tensor-parallel repositories

Trending repositories tagged tensor-parallel, ranked by trending score. Updated daily.

  1. 1
    Elevatormusic/DeepSeek-V4.1-Flash-1017-EXL3-TensorFold-2x-DGX-Spark

    DeepSeek-V4.1-Flash-1017 EXL3 2.9bpw on 2x NVIDIA DGX Spark (GB10) with TensorFold: 2.1-2.3x the vLLM kit's decode speed.

    GitHub · Python · 85 stars · 12 forks · +7 stars in 24 hours · Trending score 1.51

  2. 2
    hyukudan/strix-halo-engine-lab

    C++ inference on AMD Strix Halo (one node or USB4 pair) and NVIDIA RTX PRO 6000. Engines for Qwen3.8-Flash-Next, Qwen3.8-27B, DeepSeek V4.1 Flash, GLM-5.3 Flash, Hy4-flash, MiniMax M3.1 Flash, MiniMax H3, MiniMax-H3-Image and Nemotron 3.5 Bolt E4B.

    GitHub · C++ · 39 stars · 8 forks · +2 stars in 24 hours · Trending score 1.32

  3. 3
    Red-Weasel/machx-inference-engine

    C++/SYCL local LLM inference for Intel Arc: Qwen3.8, DeepSeek-V4.1, MiMo-V2.6, GLM-5.3 and LTX-2.5 text-to-video on Arc Pro B70 cards. XMX kernels, quantized models, multi-GPU.

    GitHub · C++ · 13 stars · 3 forks · +1 stars in 24 hours · Trending score 0.63

  4. 4
    kindlingai/gr8

    A from-scratch CUDA inference engine for 1-6 DGX Sparks (GB10): GLM-5.3, GLM-5.3-Flash and DeepSeek-V4.1-Flash

    GitHub · Cuda · 87 stars · 16 forks · 0 stars in 24 hours · Trending score 0.47

  5. 5
    yunwei37/dgx-spark-4-ring-no-switch

    Reproducible LLM inference on four NVIDIA DGX Spark (GB10) nodes wired as a direct switchless ConnectX ring — serving profiles, ring launchers, pinned ARM64 runtime images and measured results, newest tested model first.

    GitHub · Python · 21 stars · 4 forks · +1 stars in 24 hours · Trending score 0.45

  6. 6
    123123213weqw/dual-v100-llama.cpp

    Reproducible llama.cpp kernel and runtime optimization lab for dual NVIDIA Tesla V100 GPUs (SM70)

    GitHub · Python · 12 stars · 0 forks · 0 stars in 24 hours · Trending score 0.39

  7. 7
    pepuscz/strix-halo-llm

    DeepSeek-V4.1-Flash (1M context) and GLM-5.3-Flash on a BOSGAME M5 (Ryzen AI Max+ 395, Radeon 8060S, 128 GiB) with two RX 7900 XTX over OCuLink: pinned Ansible recipes and measured results. Also the M5-only Qwen and DeepSeek setups.

    GitHub · Python · 31 stars · 2 forks · 0 stars in 24 hours · Trending score 0.20

  8. 8
    jiayuqi7813/crack-open-models-dgx-spark

    Architecture-first Codex skill for open-model behavioral interventions on dual DGX Spark

    GitHub · Python · 73 stars · 25 forks · 0 stars in 24 hours · Trending score 0.15

  9. 9
    harleyszhang/rapid_llm

    RapidLLM is an LLM inference framework with continuous batching, tensor and data parallelism, quantized weights, and with pluggable Triton/CUDA kernels.

    GitHub · Python · 195 stars · 33 forks · 0 stars in 24 hours · Trending score 0.00

  10. 10
    Reederey87/glm53-flash-exl3-2x-dgx-spark

    GLM-5.3-Flash EXL3 (320B MoE) on 2x NVIDIA DGX Spark — production serving kit, 1M context, 97%+ multi-session prefix caching, DFlash2 spec decode

    GitHub · Python · 65 stars · 5 forks · 0 stars in 24 hours · Trending score 0.00

  11. 11
    kk-pcl/sglang-qwen38-dual-3080-patch

    Minimal SGLang patch for Qwen3.8-27B + DFlash2 on dual RTX 3080: TP-sharded Draft fc and static per-head FP8 KV.

    GitHub · Python · 18 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00